{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T08:19:50Z","timestamp":1775031590751,"version":"3.50.1"},"reference-count":38,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T00:00:00Z","timestamp":1644192000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T00:00:00Z","timestamp":1644192000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Schmidt Futures Foundation","award":["922"],"award-info":[{"award-number":["922"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Resource allocation problems are often approached with linear programming techniques. But many concrete allocation problems in the experimental and observational sciences cannot or should not be expressed in the form of linear objective functions. Even if the objective is linear, its parameters may not be known beforehand because they depend on the results of the experiment for which the allocation is to be determined. To address these challenges, we present a bipartite graph neural network (GNN) architecture for trainable resource allocation strategies. Items of value and constraints form the two sets of graph nodes, which are connected by edges corresponding to possible allocations. The GNN is trained on simulations or past problem occurrences to maximize any user-supplied, scientifically motivated objective function, augmented by an infeasibility penalty. The amount of feasibility violation can be tuned in relation to any available slack in the system. We apply this method to optimize the astronomical target selection strategy for the highly multiplexed Subaru Prime Focus Spectrograph instrument, where it shows superior results to direct gradient descent optimization and extends the capabilities of the currently employed solver which uses linear objective functions. The development of this method enables fast adjustment and deployment of allocation strategies, statistical analyses of allocation patterns, and fully differentiable, science-driven solutions for resource allocation problems.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac4d12","type":"journal-article","created":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T22:27:45Z","timestamp":1642631265000},"page":"015023","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Graph neural network-based resource allocation strategies for multi-object spectroscopy"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0042-9873","authenticated-orcid":true,"given":"Tianshu","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8873-5065","authenticated-orcid":true,"given":"Peter","family":"Melchior","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2022,2,7]]},"reference":[{"key":"mlstac4d12bib1","first-page":"pp 1","article-title":"Graph-based resource allocation with conflict avoidance for V2V broadcast communications","author":"Abanto-Leon","year":"2017"},{"key":"mlstac4d12bib2","article-title":"Differentiable convex optimization layers","author":"Agrawal","year":"2019"},{"key":"mlstac4d12bib3","article-title":"OptNet: differentiable optimization as a layer in neural networks","author":"Amos","year":"2017"},{"key":"mlstac4d12bib4","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"mlstac4d12bib5","doi-asserted-by":"publisher","first-page":"3143","DOI":"10.1093\/mnras\/stz1182","article-title":"UniverseMachine: the correlation between galaxy growth and dark matter halo assembly from z\u2009=\u20090\u201310","volume":"488","author":"Behroozi","year":"2019","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac4d12bib6","author":"Bertsekas","year":"1998"},{"key":"mlstac4d12bib7","doi-asserted-by":"publisher","first-page":"2276","DOI":"10.1086\/344761","article-title":"An efficient targeting strategy for multiobject spectrograph surveys: the sloan digital sky survey \u201ctiling\u201d algorithm","volume":"125","author":"Blanton","year":"2003","journal-title":"Astron. J."},{"key":"mlstac4d12bib8","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1287\/opre.43.4.670","article-title":"The nonlinear resource allocation problem","volume":"43","author":"Bretthauer","year":"1995","journal-title":"Oper. Res."},{"key":"mlstac4d12bib9","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1093\/mnras\/stz2544","article-title":"The VANDELS survey: the star-formation histories of massive quiescent galaxies at 1.0<z<1.3","volume":"490","author":"Carnall","year":"2019","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac4d12bib10","article-title":"Unsupervised resource allocation with graph neural networks","author":"Cranmer","year":"2021"},{"key":"mlstac4d12bib11","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1287\/opre.5.2.266","article-title":"Discrete-variable extremum problems","volume":"5","author":"Dantzig","year":"1957","journal-title":"Oper. Res."},{"key":"mlstac4d12bib12","article-title":"DC3: a learning method for optimization with hard constraints","author":"Donti","year":"2021"},{"key":"mlstac4d12bib13","article-title":"Backpropagation learning for systems with discrete-valued functions","volume":"vol 3","author":"Edward","year":"1994"},{"key":"mlstac4d12bib14","article-title":"Dark energy survey year 3 results: measuring the survey transfer function with Balrog","author":"Everett","year":"2020"},{"key":"mlstac4d12bib15","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1287\/opre.34.6.909","article-title":"The greedy procedure for resource allocation problems: necessary and sufficient conditions for optimality","volume":"34","author":"Federgruen","year":"1986","journal-title":"Oper. Res."},{"key":"mlstac4d12bib16","article-title":"Fast graph representation learning with PyTorch geometric","author":"Fey","year":"2019"},{"key":"mlstac4d12bib17","first-page":"pp 1","article-title":"Resource allocation via graph neural networks in free space optical fronthaul networks","author":"Gao","year":"2020"},{"key":"mlstac4d12bib18","doi-asserted-by":"publisher","first-page":"A135","DOI":"10.1051\/0004-6361\/201936329","article-title":"The stellar-to-halo mass relation over the past 12 Gyr: I. Standard \u039bCDM model","volume":"634","author":"Girelli","year":"2020","journal-title":"Astron. Astrophys. Suppl. Ser."},{"key":"mlstac4d12bib19","doi-asserted-by":"publisher","first-page":"110","DOI":"10.3847\/1538-4357\/abca35","article-title":"TARDIS. II. Synergistic density reconstruction from Ly\u03b1 forest and spectroscopic galaxy surveys with applications to protoclusters and the cosmic web","volume":"906","author":"Horowitz","year":"2021","journal-title":"Astrophys. J."},{"key":"mlstac4d12bib20","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1109\/JSAC.2008.080919","article-title":"Auction-based resource allocation for cooperative communications","volume":"26","author":"Huang","year":"2008","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"mlstac4d12bib21","doi-asserted-by":"publisher","first-page":"036","DOI":"10.1088\/1475-7516\/2015\/01\/036","article-title":"Past and present cosmic structure in the SDSS DR7 main sample","volume":"2015","author":"Jasche","year":"2015","journal-title":"J. Cosmol. Astropart. Phys."},{"key":"mlstac4d12bib22","first-page":"pp 905","author":"Katoh","year":"1998"},{"key":"mlstac4d12bib23","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"mlstac4d12bib24","doi-asserted-by":"publisher","first-page":"24","DOI":"10.3847\/0067-0049\/224\/2\/24","article-title":"The COSMOS2015 catalog: exploring the 1<z<6 universe with half a million galaxies","volume":"224","author":"Laigle","year":"2016","journal-title":"Astrophys. J. Suppl. Ser."},{"key":"mlstac4d12bib25","doi-asserted-by":"publisher","first-page":"2634","DOI":"10.1016\/j.ifacol.2020.12.378","article-title":"Resource allocation in large-scale wireless control systems with graph neural networks","volume":"53","author":"Lima","year":"2020","journal-title":"IFAC-PapersOnLine"},{"key":"mlstac4d12bib26","article-title":"Data-collection for the sloan digital sky survey: a network-flow heuristic","author":"Lupton","year":"2002"},{"key":"mlstac4d12bib27","doi-asserted-by":"publisher","first-page":"A17","DOI":"10.1051\/0004-6361\/201834256","article-title":"Selection functions of large spectroscopic surveys","volume":"621","author":"Mints","year":"2019","journal-title":"Astron. Astrophys. Suppl. Ser."},{"key":"mlstac4d12bib28","article-title":"Solving mixed integer programs using neural networks","author":"Nair","year":"2020"},{"key":"mlstac4d12bib29","doi-asserted-by":"crossref","DOI":"10.3847\/1538-3881\/ac0c13","article-title":"Selection functions in astronomical data modeling, with the space density of white dwarfs as worked example","author":"Rix","year":"2021"},{"key":"mlstac4d12bib30","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1093\/mnras\/stw2372","article-title":"The clustering of galaxies in the completed SDSS-III baryon oscillation spectroscopic survey: observational systematics and baryon acoustic oscillations in the correlation function","volume":"464","author":"Ross","year":"2017","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac4d12bib31","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1093\/mnras\/staa727","article-title":"The synthetic emission line COSMOS catalogue: H\u03b1 and [OII] galaxy luminosity functions and counts at 0.3<z<2.5","volume":"494","author":"Saito","year":"2020","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"mlstac4d12bib32","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1038\/s41550-019-0955-0","article-title":"Sub one per cent mass fractions of young stars in red massive galaxies","volume":"4","author":"Salvador-Rusi\u00f1ol","year":"2019","journal-title":"Nat. Astron."},{"key":"mlstac4d12bib33","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.jda.2015.06.001","article-title":"A faster algorithm for the resource allocation problem with convex cost functions","volume":"34","author":"Shi","year":"2015","journal-title":"J. Discrete Algorithms"},{"key":"mlstac4d12bib34","doi-asserted-by":"publisher","first-page":"R1","DOI":"10.1093\/pasj\/pst019","article-title":"Extragalactic science, cosmology and galactic archaeology with the Subaru prime focus spectrograph","volume":"66","author":"Takada","year":"2014","journal-title":"Publ. Astron. Soc. Japan"},{"key":"mlstac4d12bib35","doi-asserted-by":"publisher","DOI":"10.1117\/12.2232103","article-title":"Prime focus spectrograph (PFS) for the Subaru telescope: overview, recent progress and future perspectives","volume":"9908","author":"Tamura","year":"2016","journal-title":"Proc. SPIE"},{"key":"mlstac4d12bib36","article-title":"Differentiation of blackbox combinatorial solvers","author":"Vlastelica","year":"2020"},{"key":"mlstac4d12bib37","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.76.011115","article-title":"Inference and optimization of real edges on sparse graphs: a statistical physics perspective","volume":"76","author":"Wong","year":"2007","journal-title":"Phys. Rev. E"},{"key":"mlstac4d12bib38","first-page":"pp 3391","article-title":"Deep sets","volume":"vol 30","author":"Zaheer","year":"2017"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac4d12","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac4d12\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac4d12","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac4d12\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac4d12\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac4d12\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac4d12\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac4d12\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T12:46:34Z","timestamp":1644237994000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac4d12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,7]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,2,7]]},"published-print":{"date-parts":[[2022,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac4d12","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,7]]},"assertion":[{"value":"Graph neural network-based resource allocation strategies for multi-object spectroscopy","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2021-10-01","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-01-19","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-02-07","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}